Machine Learning for Subsurface Characterization PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Machine Learning for Subsurface Characterization PDF full book. Access full book title Machine Learning for Subsurface Characterization by Siddharth Misra. Download full books in PDF and EPUB format.
Author: Siddharth Misra
Publisher: Gulf Professional Publishing
ISBN: 0128177373
Category : Technology & Engineering
Languages : en
Pages : 442
Get Book
Book Description
Machine Learning for Subsurface Characterization develops and applies neural networks, random forests, deep learning, unsupervised learning, Bayesian frameworks, and clustering methods for subsurface characterization. Machine learning (ML) focusses on developing computational methods/algorithms that learn to recognize patterns and quantify functional relationships by processing large data sets, also referred to as the "big data." Deep learning (DL) is a subset of machine learning that processes "big data" to construct numerous layers of abstraction to accomplish the learning task. DL methods do not require the manual step of extracting/engineering features; however, it requires us to provide large amounts of data along with high-performance computing to obtain reliable results in a timely manner. This reference helps the engineers, geophysicists, and geoscientists get familiar with data science and analytics terminology relevant to subsurface characterization and demonstrates the use of data-driven methods for outlier detection, geomechanical/electromagnetic characterization, image analysis, fluid saturation estimation, and pore-scale characterization in the subsurface. Learn from 13 practical case studies using field, laboratory, and simulation data Become knowledgeable with data science and analytics terminology relevant to subsurface characterization Learn frameworks, concepts, and methods important for the engineer’s and geoscientist’s toolbox needed to support
Author: Siddharth Misra
Publisher: Gulf Professional Publishing
ISBN: 0128177373
Category : Technology & Engineering
Languages : en
Pages : 442
Get Book
Book Description
Machine Learning for Subsurface Characterization develops and applies neural networks, random forests, deep learning, unsupervised learning, Bayesian frameworks, and clustering methods for subsurface characterization. Machine learning (ML) focusses on developing computational methods/algorithms that learn to recognize patterns and quantify functional relationships by processing large data sets, also referred to as the "big data." Deep learning (DL) is a subset of machine learning that processes "big data" to construct numerous layers of abstraction to accomplish the learning task. DL methods do not require the manual step of extracting/engineering features; however, it requires us to provide large amounts of data along with high-performance computing to obtain reliable results in a timely manner. This reference helps the engineers, geophysicists, and geoscientists get familiar with data science and analytics terminology relevant to subsurface characterization and demonstrates the use of data-driven methods for outlier detection, geomechanical/electromagnetic characterization, image analysis, fluid saturation estimation, and pore-scale characterization in the subsurface. Learn from 13 practical case studies using field, laboratory, and simulation data Become knowledgeable with data science and analytics terminology relevant to subsurface characterization Learn frameworks, concepts, and methods important for the engineer’s and geoscientist’s toolbox needed to support
Author: Ramil Surhay Oglu Ahmadov
Publisher: Stanford University
ISBN:
Category :
Languages : en
Pages : 195
Get Book
Book Description
This dissertation addresses recurrent questions in hydrocarbon reservoir characteri¬zation. In particular, the major focus of this research volume is microtextural characterization of source rock fabric as well as elastic and transport properties of source rocks. Source rocks are one of the most complicated and intriguing natural materials on earth. Their multiphase composition is continually evolving over various scales of length and time, creating the most heterogeneous class of rocks in existence. The heterogeneities are present from the submicroscopic scale to the macroscopic scale, and all contribute to a pronounced anisotropy and large variety of shale macroscopic behavior. Moreover, the effects of the multiphase composition are amplified within organic-rich rocks that contain varying amounts of kerogen. Despite significant research into the properties of kerogen, fundamental questions remain regarding how the intrinsic rock-physics properties of the organic fraction affect the macroscopic properties of host rocks. Because we do not fully understand the elastic properties of either the organic matter or the individual clay minerals present in source rocks, seismic velocity prediction in organic-rich shales remains challenging. Conventional measurements of 'macroscopic' or 'average' properties on core plugs are not sufficient to fully address the degree of property variation within organic-rich rocks. Alternatively, most analyses of organic matter rely on samples that have been isolated by dissolving the rock matrix. The properties of the organic matter before and after such isolation may be different, and all information about sample orientation is lost. In addition, comprehensive characterization of organic-rich rocks has been hindered by several factors: sample preparation is time-consuming, and the nanogranular nature of this rock type makes it difficult to link effective elastic properties to maceral properties, such as elastic moduli, composition, maturity, and quality. These difficulties have prevented us from building large databases, without which we cannot establish the accurate rock-physics models needed for inverting field geophysical data. I approach this issue using atomic-force microscopy based nanoindentation, coupled with scanning electron and confocal laser-scanning microscopy as a tool for visualization and identification of the organic part within shale, and to perform nanoscale elastic-property measurements. First, the microfabric of a set of source rock samples is characterized. The spatial and temporal link between organic matter and the stiff silicate mineral matrix is established, which leads to proposal of alternative Rock Physics modeling approach to organic-rich source rocks. Based on the nanoindentation measurements, I obtain elastic properties of source rock phases and provide several applications of these (nanoindentation-derived) elastic properties within a number of geomechanical problems. Finally, transport properties of various source rock formations are discussed based on comparison to more conventional reservoir rocks.
Author: Mehdi Ostadhassan
Publisher: Springer
ISBN: 3319760874
Category : Technology & Engineering
Languages : en
Pages : 89
Get Book
Book Description
This book summarizes the authors' extensive experience and interdisciplinary approach to demonstrate how acquiring and integrating data using a variety of analytical equipment can provide better insights into unconventional shale reservoir rocks and their constituent components. It focuses on a wide range of properties of unconventional shale reservoirs, discussing the use of conventional and new analytical methods for detailed measurements of mechanical properties of both organic and inorganic constituent elements as well as of the geochemical characteristics of organic components and their origins. It also addresses the investigation of porosity, pore size and type from several perspectives to help us to define unconventional shale formation. All of these analyses are treated individually, but brought together to present the rock sample on a macro scale. This book is of interest to researchers and graduate students from various disciplines, such as petroleum, civil, and mechanical engineering, as well as from geoscience, geology, geochemistry and geophysics. The methods and approaches can be further extended to biology and medicine.
Author: Larry W. Lake
Publisher: Academic Press
ISBN:
Category : Nature
Languages : en
Pages : 752
Get Book
Book Description
Intended for petroleum engineers, geologists and hydrologists, this book provides a detailed survey of the current practices, problems, research and trends in the field of reservoir characterization. Topics discussed include mesoscopic, macroscopic and megascopic scales.
Author: Larry W. Lake
Publisher:
ISBN:
Category : Engineering geology
Languages : en
Pages : 688
Get Book
Book Description
Author: Bodhisatwa Hazra
Publisher: Springer
ISBN: 9783030130442
Category : Technology & Engineering
Languages : en
Pages : 142
Get Book
Book Description
This book details the analytical processes, and interpretation of the resulting data, needed in order to achieve a comprehensive source-rock evaluation of organic-rich shales. The authors employ case studies on Permian and Cretaceous shales from various Indian basins and other petroleum-bearing basins around the world to illustrate the key features of their organic-rich shale characterization methodology. These case studies may also help to identify potential zones within shale formations that could be exploited for commercial gas and/or oil production. Given its scope, the book will be of interest to all researchers working in the field of source-rock analysis. In addition, the source-rock evaluation techniques – and the various intricacies associated with them – discussed here offer valuable material for postgraduate geology courses.
Author: Robert P. Monicard
Publisher: Editions TECHNIP
ISBN: 2710803879
Category : Core drilling
Languages : en
Pages : 182
Get Book
Book Description
This book describes porous media and how their physical, petrophysical, mechanical, electric and superficial properties are determined. The different measuring methods and the corresponding equipment are described. Core analysis (conventional or special) required for any reservoir engineering operation or for using mathematical models is explained. Analyses of sidewall cores and whole cores are also described in detail. Actual core-analysis examples are given. The book will be invaluable for engineers and technicians in laboratories dealing with the physico-chemistry of hydrocarbon fields and the hydrology of underground nappes. Specialists in reservoir engineering will also find the book particularly useful.
Author: Thomas Aczel
Publisher: ASTM International
ISBN: 0803104677
Category : Mass spectrometry
Languages : en
Pages : 153
Get Book
Book Description
Author: Quinn R. Passey
Publisher: AAPG
ISBN: 0891817506
Category : Science
Languages : en
Pages : 222
Get Book
Book Description
Author: M. R. Riazi
Publisher: ASTM International
ISBN: 9780803133617
Category : Technology & Engineering
Languages : en
Pages : 428
Get Book
Book Description
The last three chapters of this book deal with application of methods presented in previous chapters to estimate various thermodynamic, physical, and transport properties of petroleum fractions. In this chapter, various methods for prediction of physical and thermodynamic properties of pure hydrocarbons and their mixtures, petroleum fractions, crude oils, natural gases, and reservoir fluids are presented. As it was discussed in Chapters 5 and 6, properties of gases may be estimated more accurately than properties of liquids. Theoretical methods of Chapters 5 and 6 for estimation of thermophysical properties generally can be applied to both liquids and gases; however, more accurate properties can be predicted through empirical correlations particularly developed for liquids. When these correlations are developed with some theoretical basis, they are more accurate and have wider range of applications. In this chapter some of these semitheoretical correlations are presented. Methods presented in Chapters 5 and 6 can be used to estimate properties such as density, enthalpy, heat capacity, heat of vaporization, and vapor pressure. Characterization methods of Chapters 2-4 are used to determine the input parameters needed for various predictive methods. One important part of this chapter is prediction of vapor pressure that is needed for vapor-liquid equilibrium calculations of Chapter 9.
